Alibaba (Qwen) · model
Qwen3 235B 2507 benchmark scores
As of 2026-10-07, Qwen3 235B 2507 (Alibaba (Qwen)) has measured scores on 4 benchmarks and estimated scores on 20 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 82.8% | estimated ± 5.0 pp, medium confidence |
| AA-HLE | 14.3% | estimated ± 6.5 pp, medium confidence |
| Artificial Analysis Intelligence Index | 21.3% | estimated ± 3.9 pp, medium confidence |
| CritPt | 0.6% | estimated ± 4.1 pp, high confidence |
| GPQA Diamond | 77.5% | estimated ± 0.4 pp, high confidence |
| HLE | 26.8% | estimated ± 7.8 pp, medium confidence |
| AA-Omniscience Accuracy | 22.4% | estimated ± 6.0 pp, medium confidence |
| MMLU-Pro | 83.0% | measured |
| GPQA | 77.5% | measured |
| ARC-AGI-1 | 39.5% | estimated ± 6.9 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 pp, low confidence |
| Vals GPQA Diamond | 66.5% | estimated ± 4.8 pp, medium confidence |
| Vals MMLU-Pro | 59.4% | estimated ± 1.2 pp, medium confidence |
| HLE w/o tools | 10.2% | estimated ± 4.9 pp, high confidence |
| SWE Multilingual | 66.2% | estimated ± 2.6 pp, low confidence |
| C-Eval | 89.4% | estimated ± 0.7 pp, low confidence |
| MMLU-ProX | 79.4% | measured |
| MMLU-Redux | 91.9% | estimated ± 0.7 pp, high confidence |
| NOVA-63 | 54.9% | estimated ± 1.3 pp, low confidence |
| SuperGPQA | 62.6% | measured |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| HealthBench Professional | 27.2% | estimated ± 4.8 pp, low confidence |
| MMLU | 89.9% | estimated ± 3.6 pp, low confidence |